Return to BSD News archive
Path: euryale.cc.adfa.oz.au!newshost.carno.net.au!harbinger.cc.monash.edu.au!munnari.OZ.AU!news.ecn.uoknor.edu!news.wildstar.net!newsfeed.direct.ca!super.zippo.com!zdc!news.pbi.net!news.mathworks.com!news.maxwell.syr.edu!news1.best.com!nntp1.ba.best.com!not-for-mail
From: dillon@flea.best.net (Matt Dillon)
Newsgroups: comp.unix.bsd.freebsd.misc,comp.unix.bsd.bsdi.misc,comp.sys.sgi.misc
Subject: Re: no such thing as a "general user community"
Date: 27 Mar 1997 20:22:45 -0800
Organization: BEST Internet Communications, Inc.
Lines: 38
Message-ID: <5hfh2l$i13@flea.best.net>
References: <331BB7DD.28EC@net5.net> <5goqrq$5ak$1@news.clinet.fi> <5hd29s$e7t@fido.asd.sgi.com> <5he3pp$8ms$2@kayrad.ziplink.net>
NNTP-Posting-Host: flea.best.net
Xref: euryale.cc.adfa.oz.au comp.unix.bsd.freebsd.misc:37859 comp.unix.bsd.bsdi.misc:6478 comp.sys.sgi.misc:29445
:In article <5he3pp$8ms$2@kayrad.ziplink.net>,
:Mikhail Teterin <mi@ALDAN.ziplink.net..remove-after-`net'> wrote:
:>Honorable Larry McVoy
:> wrote on 27 Mar (in article <5hd29s$e7t@fido.asd.sgi.com>):
:>
:>=File & VM system latencies in microseconds - smaller is better
:>=--------------------------------------------------------------
:>=Host OS 0K File 10K File Mmap Prot Page
:>= Create Delete Create Delete Latency Fault Fault
:>=--------- ------------- ------ ------ ------ ------ ------- ----- -----
:>=P5-133 FreeBSD 2.2-C 2857 1123 4000 3225 133 -1 0.0K
:>=R10K IRIX64 6.2-no 374 389 353 387 55 -1 21.5K
:>
:>=About a factor of 10. The R10K is 2x the perf of the P5 but the FreeBSD
:>=system is sitting idle waiting for the desk. An infinitely fast CPU
:>=wouldn't help.
:>
:>From what I can see, this demonstrates the superiority of hardware,
:>rather then OS. We don't even see what kind of disk/adapter was
:>used on the machines (IDE? :)
:>
:>FreeBSD's ccd-driver used over same several disks increases the
:>speed nearly linear...
:>
:>And look! For MMap it is only 2.+ times worse! Make it a PPro-200
:>with 512 cache and SGI will loose this...
I didn't even notice that :-) A 200 MHz PPro (P6) is over twice as fast
as a 133 MHz pentium (P5). XFS will still beat out a normally mounted
ffs filesystem in terms of file creates/deletes though. It will not
beat out an async-mounted ffs filesystem, however, which means that
once ordered block I/O is put into FreeBSD, you can kiss goodbye
to that statistic. File lookups under XFS will be the only thing
left that it can boast about. This is a significant, but not
overpowering, feature.
-Matt